Aiming at the problem that ViBe (visual background extractor) algorithm is prone to ghosting during moving target detection, an improved algorithm, ViBe-BR (ViBe with background restoration) was proposed by adding a background restoration stage to the original algorithm. First, the foreground region within the background image was pre-extracted by combining three-frame differencing. Then, the interior of the region was filled using the background pixels around the foreground region to obtain the restored image; Finally, the restored image was corrected and ViBe detection was performed based on the reduced background to achieve the effect of suppressing ghosting. The experimental results show that the ViBe-BR algorithm achieves good detection results in four different scenes, and compared with the ViBe algorithm, the average precision, recall, and F₁ value of foreground detection have been improved by 0.222, 0.03, and 0.123 in that order, which effectively eliminates the influence of ghosting, and it can be applied to practical geo-localization tasks in order to obtain the geographic location information of the moving targets.

As an important firefighting equipment, fire cylinders need to undergo regular safety evaluations during their service period. In order to efficiently and accurately evaluate the safety status of fire steel cylinders, a safety evaluation model suitable for fire steel cylinders was established based on the analytic hierarchy process and fuzzy comprehensive evaluation method. The feasibility of the model was verified through case evaluation. Secondly, the BP neural network based on MPGA (multi population genetic algorithm) is used to optimize the safety evaluation model of fire steel cylinders. This method improves the process of updating weights and thresholds of the BP neural network through multi population genetic algorithm, improving the accuracy of BP neural network prediction results and the efficiency of fire steel cylinder safety evaluation. Finally, the construction of safety evaluation models for fire steel cylinders based on BP, GA-BP, and MPGA-BP was completed using Python. By comparing and analyzing the prediction results of three models, it was found that the MPGA-BP neural network has the smallest prediction error, proving that the proposed MPGA-BP safety evaluation model has high accuracy and can more efficiently and accurately evaluate the safety of fire steel cylinders.

A method for diagnosing AC series arc faults based on the Inception module and BiLSTM (bidirectional long short-term memory) was proposed to address the challenge of identifying small current changes caused by arc faults in aviation cables. First, features of the raw current data were extracted by calculating the discrete sum of squares of the autocorrelation coefficient, Shannon entropy, and wavelet energy entropy. These features are then combined to form a new feature matrix, enhancing the original data's feature representation. Subsequently, the Inception-BiLSTM network learns from the feature matrix and ultimately completes the arc fault diagnosis. To validate the diagnostic performance of the model in practical environments, a series of experiments were conducted, including vibration tests, stress tests, and wet cable tests, based on an aviation cable arc fault simulation platform, with the experimental data being integrated as detection samples. The experimental results show that the proposed method achieves a high accuracy rate of 99.69% in identifying arc faults.

Aspect-level sentiment analysis detects the sentiment polarity of given aspect terms from a fine-grained perspective, providing decision support for e-commerce, consumers, and other groups by mining textual aspect sentiment. Different syntactic dependencies were treated equally in existing methods resulting in the influence of relation types in convolutional networks and the global information from semantic perspective being overlooked. To address these issues, considering the flexibility and complexity of graph structures, the excellent performance of auxiliary tasks in capturing aspect sentiment based on global semantic information and completing fine-grained aspect information, the model WRCN-CL (weight relational convolutional networks and complementary task) which incorporates two tasks: WRCN(weighted relational convolutional networks) and CL (complementary learning) was proposed. Specifically, Bi-LSTM (bidirectional long short-term memory network) was used to extract textual features, which were entered into WRCN and CL tasks separately. Aspect-related semantic information was collected from a global perspective to enhance knowledge, while the aspect representations from CL combined with GCN (graph convolutional networks) to deeply explore syntactic information based on positional and type-aware relational information in WRCN. The fused global and local features were then input into a pooling layer to obtain comprehensive information representation for improved classification performance. Experimental results demonstrate significant improvements with the accuracy of 83.49%、78.19%、75.89% on three public datasets compared to baseline models, proving the effectiveness of the proposed model in aspect-level sentiment analysis classification task.

Due to the negative impact of abandoned powdered clay on land waste and pollution, it is beneficial to improve the powdered clay and use it for backfill in engineering construction.The effects of lignin fiber content and cement content on the unconfined compressive strength of silty clay excavated from a tunnel along the Yangtze River in Hangzhou,Zhejiang Province were studied. The formation mechanism of the compressive strength was analyzed. Finally,the pore microstructure of the sample was quantitatively analyzed by SEM experiment. The results show that the compressive strength reached the maximum value when the lignin fiber content is 4%,and the unconfined compressive strength was greater than that when the lignin fiber content is 2%, 6% and 8%. No matter how much lignin fiber content is,the unconfined compressive strength q'_u increases gradually with the increase of cement content. With the addition of lignin fiber,the average diameter of pores gradually concentrated in the range of particle size less than 1 μm,and the proportion of pores 1~2 μm and 2~4 μm increased with the increase of cement content. With the increase of lignin fiber and cement content,pore abundance mainly concentrated in the range of 0.2~0.5.With the addition of lignin fiber,the particle abundance mainly concentrated in the range of 0.1~0.6,and the particle distribution showed a “mountain” pattern with the addition of cement.

As a power drilling tool that can meet the needs of deep ground and high temperature drilling, the short life of thrust bearing is a key problem affecting drilling efficiency. Based on the CCD design method and finite element numerical simulation method, three sets of variables were selected as the design parameters, the orthogonal test between different structural parameters and abrasive wear life was carried out, and the optimal structural parameters of the bearing were determined by the range analysis method. The temperature-displacement coupling finite element model of bearing wear was established, and the influence of axial load, temperature and wear times on the wear depth of the bearing was studied considering the frictional heat generation of the bearing. The results show that the overall performance of the bearing with optimal structural parameters is improved, the stress concentration of the bearing is alleviated, the wear of the bearing is reduced, and the optimized structural life is increased by 4.6% compared with the initial life. This research method provides a reference value for the optimal design of this type of bearing. At the same time, the influence of different working conditions on bearing wear was analyzed. With the increase of axial load, the wear depth of the bearing increases. With the increase of the number of wear, the wear depth also shows an increasing trend. With the increase of bottom hole temperature, the wear depth decreases first and then increases gradually.

Clouds play a crucial role in the atmospheric dynamics of the Earth, and precise segmentation of ground-based cloud images is essential for improving the accuracy of weather forecasting. In response to issues such as varying data quality, low data volume, and different capture angles in existing open-source cloud image datasets, a labeled standard ground-based cloud image dataset (Cloud-GT) was constructed using manual annotation and transfer learning methods. The color channel component threshold segmentation method was employed to eliminate sunlight interference. Furthermore, an improved U2Net-based ground-based cloud image segmentation technique was proposed. The model introduced channel attention modules and depth-wise separable convolution modules in the feature extraction unit, which greatly reduces the network model parameters while improving the effective feature extraction of ground-based cloud maps within the network. Finally, comparing and analyzing the method with classical segmentation networks, experimental results indicated that the method achieved classification pixel accuracy, mean class pixel accuracy, average intersection over union, intersection over union, and F₁ score of 84.03%, 90.88%, 84.13%, 74.12%, and 89.59%, respectively. In comparison with U2Net, UNet, and FCN, the method demonstrated a significant improvement in performance. In conclusion, the method not only substantially reduced the model parameters but also effectively enhanced segmentation accuracy, which provides the possibility of practical application.

CO₂ flooding technology, recognized as a mature tertiary recovery method, is widely applied in complex small fault-block oilfields with strong heterogeneity. However, severe gas channeling is commonly observed during CO₂ flooding. As a result, the improvement in oil displacement efficiency remains low, typically below 10%. To address this, effective methods were explored to enhance oil displacement efficiency. Foam profile control and plugging were utilized as key techniques to achieve this enhancement.In the experiment, the JS oilfield was used as an example. The foam performance of the gas-soluble foaming plugging agent G-CF4 and the water-soluble foaming plugging agent W-CF1 was compared. The plugging agent with better foam performance was selected. Its plugging ability and oil displacement efficiency were tested.The results show that under target reservoir conditions, the optimal foaming plugging agent is 0.25% G-CF4.Moreover, the greater the permeability difference within the core combination, the stronger the plugging effect of G-CF4 in high-permeability cores.For a core combination with a permeability difference of 88 mD, the resistance coefficient of high-permeability cores is 2.5 times higher than that of a core combination with a permeability difference of 50 mD. In the core combination with 88 mD permeability difference, G-CF4 can maintain the resistance coefficient of high permeability cores above 9.2.The injection of 0.25% G-CF4 solution for 0.3 PV, followed by CO₂ flooding, improves oil displacement efficiency by 15% compared to CO₂ flooding alone.This study provides laboratory evidence supporting the optimization of foaming plugging technology in the JS oilfield.

The study focused on wrap-around reinforced soil retaining walls and proposed a calculation method for panel displacement. The horizontal displacement was divided into two components for calculation: the horizontal displacement caused by the strain of reinforcement and the overall horizontal displacement generated by the horizontal earth pressure acting on the back of the reinforced zone. When calculating the horizontal displacement caused by the reinforcement strain, the reinforced zone was divided into subzones through the potential failure surface of reinforced soil retaining wall and the natural repose angle of soil. The horizontal distribution of the reinforcement load was assumed, yielding a simplified calculation model for the horizontal displacement caused by reinforcement strain. For the calculation of the overall horizontal displacement of the reinforced zone, the zone was treated as a ‘cantilever beam’, taking into account the variation in elastic modulus of the reinforced zone with height. The theoretical results obtained through the proposed method were compared with experimental and numerical simulation results. The distribution trend of the displacements was basically consistent, indicating that the proposed method can effectively calculate the panel displacement of wrap-faced reinforced soil retaining walls.

The development of a high-grade waterway network in the Upper Yangtze River will play a crucial role in promoting the economic and social development in the Chengdu-Chongqing region. Waterway improvement through underwater blasting to removal the obstructing rocks is still one of the most effective method in mountainous river management, but its impact on aquatic organisms, particularly on passively drifting fish eggs and larvae, has raised significant ecological concerns. Long-term observational data of drifting larvae in the Upper Yangtze River were analyzed, focusing on their temporal distribution patterns and spatial variations in species composition and abundance. The propagation mechanisms of underwater blasting shock waves were examined, and the primary factors affecting shock wave intensity were identified. Current research on blast-induced fish damage was reviewed, with special attention paid to the effects of shock waves on eggs and larvae. Based on the documented drift patterns of eggs and larvae and the characteristics of shock waves, comprehensive ecological protection measures were proposed. These measures included temporal and spatial avoidance strategies, optimized blasting techniques, and the use of bubble curtain technology. These findings provide valuable insights for achieving sustainable development that balances waterway construction with ecological conservation in the Upper Yangtze River.